© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 75498
    Prev
    Next
    INDEX
    Explanations

    instances of the word "tap" and its variations, often in the context of engaging with resources or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    een
    -0.08
    edith
    -0.07
    sq
    -0.07
    erva
    -0.07
    ennent
    -0.07
    rema
    -0.07
    ivant
    -0.07
    yang
    -0.07
    er
    -0.07
    elpers
    -0.06
    POSITIVE LOGITS
     tap
    0.09
     Tap
    0.08
     tapping
    0.08
    Tap
    0.08
    VERN
    0.07
     tapped
    0.07
     brakes
    0.07
    αν
    0.07
    azole
    0.07
    ster
    0.06
    Activations Density 0.007%

    No Known Activations